© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14885
    Prev
    Next
    INDEX
    Explanations

    phrases related to government officials and military topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1108
    +0.12
    0.3%
    1415
    +0.09
    0.3%
    2016
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.12
    0.02
    2016
    +0.09
    0.05
    441
    +0.09
    0.04
    Negative Logits
    <bos>
    -0.64
     prêtres
    -0.63
    kinci
    -0.57
     skimage
    -0.56
     riguard
    -0.56
     tolu
    -0.55
     provinciale
    -0.55
     pymysql
    -0.54
     gabri
    -0.54
     créées
    -0.54
    POSITIVE LOGITS
     respectively
    0.83
     collectively
    0.75
     all
    0.73
     allemaal
    0.72
    respectively
    0.70
     모두
    0.63
     respectivamente
    0.62
    それぞれ
    0.60
    all
    0.59
     each
    0.56
    Activations Density 0.553%

    No Known Activations